{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.12.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":121150,"databundleVersionId":15061024,"isSourceIdPinned":false,"sourceType":"competition"},{"sourceId":692580,"sourceType":"modelInstanceVersion","isSourceIdPinned":false,"modelInstanceId":525132,"modelId":539167}],"dockerImageVersionId":31236,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import os\nimport pandas as pd\nimport torch\nfrom torch.utils.data import DataLoader, Dataset\nfrom transformers import AutoTokenizer, AutoModelForSeq2SeqLM\nfrom tqdm.auto import tqdm","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2025-12-25T09:00:02.179850Z","iopub.execute_input":"2025-12-25T09:00:02.180161Z","iopub.status.idle":"2025-12-25T09:00:13.172129Z","shell.execute_reply.started":"2025-12-25T09:00:02.180139Z","shell.execute_reply":"2025-12-25T09:00:13.171492Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"MODEL_PATH = \"/kaggle/input/akkadian-byt5-translator/pytorch/default/1/akkadian_byt5_trained\"","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-25T09:01:54.197262Z","iopub.execute_input":"2025-12-25T09:01:54.197594Z","iopub.status.idle":"2025-12-25T09:01:54.201559Z","shell.execute_reply.started":"2025-12-25T09:01:54.197568Z","shell.execute_reply":"2025-12-25T09:01:54.200781Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"TEST_DATA_PATH = \"/kaggle/input/deep-past-initiative-machine-translation/test.csv\"\nBATCH_SIZE = 6\nMAX_LENGTH = 256\nDEVICE = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n\ntokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)\nmodel = AutoModelForSeq2SeqLM.from_pretrained(MODEL_PATH).to(DEVICE)\nmodel.eval()\n\ntest_df = pd.read_csv(TEST_DATA_PATH)\n\nPREFIX = \"translate Akkadian to English: \"\n\nclass InferenceDataset(Dataset):\n    def __init__(self, df, tokenizer):\n        self.texts = df['transliteration'].astype(str).tolist()\n        self.texts = [PREFIX + i for i in self.texts]\n        self.tokenizer = tokenizer\n        \n    def __len__(self):\n        return len(self.texts)\n    \n    def __getitem__(self, idx):\n        text = self.texts[idx]\n        inputs = self.tokenizer(\n            text, \n            max_length=MAX_LENGTH, \n            padding=\"max_length\", \n            truncation=True, \n            return_tensors=\"pt\"\n        )\n        return {\n            \"input_ids\": inputs[\"input_ids\"].squeeze(0),\n            \"attention_mask\": inputs[\"attention_mask\"].squeeze(0)\n        }\n\ntest_dataset = InferenceDataset(test_df, tokenizer)\ntest_loader = DataLoader(test_dataset, batch_size=BATCH_SIZE, shuffle=False)\n\nprint(\"Starting Inference...\")\nall_predictions = []","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-25T09:01:55.638695Z","iopub.execute_input":"2025-12-25T09:01:55.639301Z","iopub.status.idle":"2025-12-25T09:02:31.635759Z","shell.execute_reply.started":"2025-12-25T09:01:55.639272Z","shell.execute_reply":"2025-12-25T09:02:31.635017Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"with torch.no_grad():\n    for batch in tqdm(test_loader):\n        input_ids = batch[\"input_ids\"].to(DEVICE)\n        attention_mask = batch[\"attention_mask\"].to(DEVICE)\n  \n        outputs = model.generate(\n            input_ids=input_ids,\n            attention_mask=attention_mask,\n            max_length=MAX_LENGTH,\n            num_beams=6,\n            early_stopping=True\n        )\n        \n        decoded = tokenizer.batch_decode(outputs, skip_special_tokens=True)\n        all_predictions.extend([d.strip() for d in decoded])","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-25T09:02:31.636961Z","iopub.execute_input":"2025-12-25T09:02:31.637211Z","iopub.status.idle":"2025-12-25T09:02:35.848313Z","shell.execute_reply.started":"2025-12-25T09:02:31.637187Z","shell.execute_reply":"2025-12-25T09:02:35.847480Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"submission = pd.DataFrame({\n    \"id\": test_df[\"id\"],\n    \"translation\": all_predictions\n})\n\nsubmission[\"translation\"] = submission[\"translation\"].apply(lambda x: x if len(x) > 0 else \"broken text\")\n\nsubmission.to_csv(\"submission.csv\", index=False)\nprint(\"Submission file saved successfully!\")\nsubmission.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-25T09:02:35.849409Z","iopub.execute_input":"2025-12-25T09:02:35.849658Z","iopub.status.idle":"2025-12-25T09:02:35.874047Z","shell.execute_reply.started":"2025-12-25T09:02:35.849630Z","shell.execute_reply":"2025-12-25T09:02:35.873369Z"}},"outputs":[],"execution_count":null}]}